Pulmonary CT nodules segmentation using an enhanced square U-Net with depthwise separable convolution

Ji Li; Jiabao Jin; Dongfang Shen; Guanping Xu; Hui-Qing Zeng; Sunkui Ke; Xiangxing Chen; Miao Wang; Xiongbiao Luo

doi:10.1117/12.2654272

3 April 2023 Pulmonary CT nodules segmentation using an enhanced square U-Net with depthwise separable convolution

Ji Li, Jiabao Jin, Dongfang Shen, Guanping Xu, Hui-Qing Zeng, Sunkui Ke, Xiangxing Chen, Miao Wang, Xiongbiao Luo

Proceedings Volume 12464, Medical Imaging 2023: Image Processing; 124643Y (2023) https://doi.org/10.1117/12.2654272
Event: SPIE Medical Imaging, 2023, San Diego, California, United States

Conference Poster

Abstract

Accurate pulmonary nodule segmentation in computed tomography (CT) images is of great importance for early diagnosis and analysis of lung diseases. Although deep convolutional networks driven medical image analysis methods have been reported for this segmentation task, it is still a challenge to precisely extract them from CT images due to various types and shapes of lung nodules. This work proposes an effective and efficient deep learning framework called enhanced square U-Net (ESUN) for accurate pulmonary nodule segmentation. We trained and tested our proposed method on publicly available data LUNA16. The experimental results showing that our proposed method can achieve Dice coefficient of 0.6896 better than other approaches with high computational efficiency, as well as reduce the network parameters significantly from 44.09M to 7.36M.

Citation Download Citation

Ji Li, Jiabao Jin, Dongfang Shen, Guanping Xu, Hui-Qing Zeng, Sunkui Ke, Xiangxing Chen, Miao Wang, and Xiongbiao Luo "Pulmonary CT nodules segmentation using an enhanced square U-Net with depthwise separable convolution", Proc. SPIE 12464, Medical Imaging 2023: Image Processing, 124643Y (3 April 2023); https://doi.org/10.1117/12.2654272

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available